Google DeepMind's Veo 3 is Now Image to Video + Audio
Aka I2V+A
Google DeepMind just rolled out a major update to its image-to-video tool, and the results are impressive.
I ran a quick test using images generated with Midjourney and Runway’s Frames, and brought them to life with synced video and generated sound in Veo 3.
First Impressions
Veo really wants to sing—even when you don’t ask it to
Character voices lack consistency between shots
It handles both photoreal and animated content well
No more surprise subtitles in your clips
What’s New in Veo 3:
Speech from still images (beta)
Fast mode for quicker and cheaper renders
Top-up credits for Pro users (no Ultra upgrade needed)
Improved audio syncing, fewer subtitle bugs
Latency improvements and bug fixes across the board
It’s still early days, but this moves us one step closer to fully generative scenes from a single frame. More thoughts coming soon.
Be Well, Do Good and Make Awesome Things!
-Gabe Michael
About the Author
Gabe Michael is an award-winning AI filmmaker and creative technologist shaping the future of production with AI. He currently serves as VP and Executive Producer of AI at Edelman, where he consults internal and external teams, enhances production workflows and explores new creative possibilities with AI.
As an early adopter of AI technology in film, video and creative production, Gabe’s work has earned accolades for ‘Best Odyssey’ at Project Odyssey, ‘Best Character’ and ‘Best Art Direction’ at the Runway Gen:48 AI Film Competitions, leading to his entry into many creative partner programs with top AI video tools.
With extensive experience as a director and producer in the creator economy, Gabe collaborates with top film studios, brands, and digital platforms, and shares his expertise on LinkedIn, YouTube, and in classrooms at UCLA.
📍 Website: gabemichael.ai
📺 YouTube: Gabe Michael’s Channel
📷 Instagram: @gabemichael_ai
📝 Substack: The Creative Possible
💼 LinkedIn: Gabe Michael